A New Path Forward.

Canvas Dx is the first FDA-authorized1 Software as a Medical Device (SaMD)2 that aids physicians in diagnosing autism spectrum disorder (ASD) in young children3

Canvas Dx harnesses clinically validated3 artificial intelligence (AI) technology to aid physicians in diagnosing ASD in children between the ages of 18 and 72 months who are at risk of developmental delay

Canvas Dx has the potential to facilitate early diagnosis in children with ASD3

How does Canvas Dx work?

Canvas Dx incorporates 3 separate, user-friendly inputs:3

kid playing
mobile phone icon

A parent/caregiver questionnaire that asks about the child’s behavior and development collected via a parent/caregiver facing app

mom with phone camera
yt play button icon

2 videos of the child interacting in their natural environment, recorded by the caregiver, then analyzed by a specially-trained video analyst*

mom and daughter consultation
List icon

An HCP questionnaire completed by a physician** who meets with the child and a parent/caregiver, collected via a healthcare provider portal

*Trained professional with at least a Master's degree and at least 5 years diagnosing and/or treating children with ASD.
**One of Canvas Dx’s device inputs is a 13 or 15 item age-dependent healthcare provider (HCP) questionnaire collected via a healthcare provider portal. 

The Canvas Dx algorithm then evaluates all 3 inputs, generating a device output that the Primary Care Physician (PCP) utilizes in combination with their clinical judgement3

For Caregivers

User Guide

For Healthcare Providers

User Guide

Because most ASD-specific interventions require a formal ASD diagnosis, delays can result in missed opportunities during a critical window in the child’s neurodevelopment11,21

Why Canvas Dx?

Canvas Dx can aid PCPs in diagnosing ASD in children starting at 18 months of age3 during a critical period when interventions are shown to provide/lead to improved long-term outcomes.4-8

While a child as young as 18 months can be reliably diagnosed with ASD,9 multiple factors have driven the average age of diagnosis to 4 years and 2 months,10 an average delay of 3 years between parental concern and a formal ASD diagnosis.11

calendar

Long Wait Times

A shortage of specialists 12,13 and time-intensive evaluations14,15 result in long wait times for diagnostic appointments, causing substantial delays in diagnosis.16

Doorway

Lack of Access

Children who are non-white, female, from rural areas or from disadvantaged socioeconomic backgrounds are often diagnosed later than the average delay reported or missed altogether.17-19

Clock

Delayed Referrals

Because there is no standard diagnostic process for ASD and there are multiple types of specialists for referral, there is no clear pathway for PCPs.20

How AI Works


AI uses pattern recognition to uncover clinically meaningful relationships that exist between signs, symptoms, and behaviors. In addition, AI approaches are suitable for aiding medical diagnosis. They can unlock clinically relevant information hidden in healthcare data and identify complex non-linear patterns between patient features and diagnosis.22-25


How Canvas Dx Works

Canvas Dx harnesses the power of artificial intelligence (AI) to aid primary care physicians (PCPs) in the identification of autism spectrum disorder (ASD).3

Canvas Dx's AI / machine learning algorithm can be optimized to improve accuracy by training on new data.

The Canvas Dx algorithm (v2) was optimized by training on new data
and has the following performance metrics:

  • Negative Predictive Value (NPV) of 95.6%
  • Positive Predictive Value (PPV) of 87.5%
  • Determinate rate (rate for Canvas Dx to provide either a positive or negative for ASD result) of 66.5%

Good machine learning practices26 were followed in the algorithm update, as the industry standard in the field of AI/ML.

npv-ppv

Pivotal Study Results

The Canvas Dx pivotal study measured the performance of the Device with algorithm v1 in aiding the diagnosis of autism spectrum disorder (ASD), compared to specialist evaluation using DSM-5 criteria.3

alt text

The accuracy of Canvas Dx was assessed in comparison to the standard diagnostic approach (specialist evaluation and diagnosis) in a multisite, prospective, double-blinded, active comparator cohort study. The study included 425 children, aged 18-72 months, with parental or PCP concern for developmental delay.3


Access the Pivotal Study
Smiling people

How Canvas Dx Helps

Accurate

When used in conjunction with a physician's clinical assessment, Canvas Dx can accurately aid diagnosis starting at 18 months of age3 during a critical window in a child’s neurodevelopment.4

Efficient

By helping PCPs diagnose or rule out ASD, remotely or in person, Canvas Dx has the potential to expand the group of diagnosing physicians and may allow for more efficient specialty referrals.3

Use of Canvas Dx may allow children with ASD to be diagnosed over 1.5 years earlier than the current average age of diagnosis3,10

The average age of children with a positive output in the Canvas Dx pivotal trial was 2.8 years3, whereas the current average age of diagnosis is 4 years, 2 months10

For medical inquiries, please contact Cognoa Medical Affairs at medaffairs@cognoa.com

© Cognoa 2023

+

Canvas Dx is intended for use by healthcare providers as an aid in the diagnosis of Autism Spectrum Disorder (ASD) for patients ages 18 months through 72 months who are at risk for developmental delay based on concerns of a parent, caregiver, or healthcare provider. The device is not intended for use as a stand-alone diagnostic device but as an adjunct to the diagnostic process. The device is for prescription use only (Rx only).

There are no contraindications to using Canvas Dx. 

The Device is intended for use by healthcare professionals trained and qualified to interpret the results of a behavioral assessment examination and to diagnose ASD.

The Device is intended for use in conjunction with patient history, clinical observations, and other clinical evidence the HCP determines are necessary before making clinical decisions. For instance, additional standardized testing may be sought to confirm the Device output, especially when the Device result is not Positive or Negative for ASD.

Canvas Dx is intended for patients with caregivers who have functional English capability (8th grade reading level or above) and have access to a compatible smartphone with an internet connection in the home environment.

The Device may give unreliable results if used in patients with other conditions that would have excluded them from the clinical study. Among those conditions are the following:

  • Suspected auditory or visual hallucinations or with prior diagnosis of childhood onset schizophrenia
  • Known deafness or blindness
  • Known physical impairment affecting their ability to use their hands
  • Major dysmorphic features or prenatal exposure to teratogens such as fetal alcohol syndrome
  • History or diagnosis of genetic conditions (such as Rett syndrome or Fragile X)
  • Microcephaly
  • History or prior diagnosis of epilepsy or seizures
  • History of or suspected neglect
  • History of brain defect injury or insult requiring interventions such as surgery or chronic medication

The Device evaluation should be completed within 60 days of the time it is prescribed because neurodevelopmental milestones change rapidly in the indicated age group.

  1. U.S. Food & Drug Administration. FDA Authorizes Marketing of Diagnostic Aid for Autism Spectrum Disorder. .https://www.fda.gov/news-events/press-announcements/fda-authorizes-marketing-diagnostic-aid-autism-spectrum-disorder.  (2021) 
  2. U.S. Food & Drug Administration. Software as a Medical Device (SaMD). https://www.fda.gov/medical-devices/digital-health-center-excellence/software-medical-device-samd. (2018)
  3. Megerian, J. T., Dey, S., Melmed, R. D., Coury, D. L., Lerner, M., Nicholls, C. J., ... & Taraman, S. (2022). Evaluation of an artificial intelligence-based medical device for diagnosis of autism spectrum disorder. NPJ digital medicine, 5(1), 1-11.
  4. Koegel, L. K., Koegel, R. L., Ashbaugh, K. & Bradshaw, J. The importance of early identification and intervention for children with or at risk for autism spectrum disorders. Int. J. Speech Lang. Pathol. 16, 50–56 (2014).
  5. Anderson, D. K., Liang, J. W. & Lord, C. Predicting young adult outcome among more and less cognitively able individuals with autism spectrum disorders. J. Child Psychol. Psychiatry 55, 485–494 (2014).
  6. Estes, A. et al. Long-term outcomes of early intervention in 6-year-old children with autism spectrum disorder. J. Am. Acad. Child Adolesc. Psychiatry 54, 580–587 (2015).
  7. Vivanti, G., Dissanayake, C., & The Victorian ASELCC Team. Outcome for Children Receiving the Early Start Denver Model Before and After 48 Months. J. Autism Dev. Disord. 46, 2441–2449 (2016).
  8. Peters-Scheffer, N., Didden, R., Korzilius, H. & Sturmey, P. A meta-analytic study on the effectiveness of comprehensive ABA-based early intervention programs for children with autism spectrum disorders. Res. Autism Spectr. Disord. 5, 60–69 (2011).
  9. Pierce, K. et al. Evaluation of the diagnostic stability of the early autism spectrum disorder phenotype in the general population starting at 12 months. JAMA Pediatr. 173, 578–587 (2019).
  10. Maenner, M. J., Shaw, K. A., Bakian, A. V. & et al. Prevalence and Characteristics of Autism Spectrum Disorder Among Children Aged 8 Years — Autism and Developmental Disabilities Monitoring Network, 11 Sites, United States, 2018. MMWR Surveill Summ 2021 70, 1–16 (2021).
  11. Zuckerman, K. E., Lindly, O. J. & Sinche, B. K. Parental Concerns, Provider Response, and Timeliness of Autism Spectrum Disorder Diagnosis. J. Pediatr. 166, 1431-1439.e1 (2015).
  12. Rimsza, M. E., Ruch-Ross, H. S., Clemens, C. J., Moskowitz, W. B. & Mulvey, H. J. Workforce trends and analysis of selected pediatric subspecialties in the United States. Acad. Pediatr. 18, 805–812 (2018).
  13. American Academy of Child & Adolescent Psychiatry. AACAP Releases Workforce Maps Illustrating Severe Shortage of Child and Adolescent Psychiatrists. (2018).
  14. Kaufman, N. K. Rethinking “gold standards” and “best practices” in the assessment of autism. Appl. Neuropsychol. Child 1–12 (2020).
  15. Randall, M. et al. Diagnostic tests for autism spectrum disorder (ASD) in preschool children. Cochrane Database Syst. Rev. (2018).
  16. Gordon-Lipkin, E., Foster, J. & Peacock, G. Whittling down the wait time: exploring models to minimize the delay from initial concern to diagnosis and treatment of autism spectrum disorder. Pediatr. Clin. 63, 851–859 (2016).
  17. Broder-Fingert, S., Mateo, C. M. & Zuckerman, K. E. Structural Racism and Autism. Pediatrics 146, e2020015420 (2020).
  18. Aylward, B. S., Gal-Szabo, D. E. & Taraman, S. Racial, Ethnic, and Sociodemographic Disparities in Diagnosis of Children with Autism Spectrum Disorder. J. Dev. Behav. Pediatr. JDBP (2021).
  19. Wiggins, L. D. et al. Disparities in Documented Diagnoses of Autism Spectrum Disorder Based on Demographic, Individual, and Service Factors. Autism Res. 13, 464–473 (2020).
  20. Goin-Kochel, R. P., Mackintosh, V. H. & Myers, B. J. How many doctors does it take to make an autism spectrum diagnosis? Autism 10, 439–451 (2006).
  21. Oswald, D. P., Haworth, S. M., Mackenzie, B. K. & Willis, J. H. Parental report of the diagnostic process and outcome: ASD compared with other developmental disabilities. Focus Autism Dev. Disabil. 32, 152–160 (2017).
  22. Shannon, J., Salomon, C., Chettiath, T., Abbas, H. & Taraman, S. Autism spectrum disorder and the promise of Artificial Intelligence. J Child Adolesc Behav 10, 2 (2022).
  23. Chang, A. C. Intelligence-based medicine: artificial intelligence and human cognition in clinical medicine and healthcare. Academic Press (2020).
  24. Buch, V. H., Ahmed, I. & Maruthappu, M. Artificial intelligence in medicine: current trends and future possibilities. Br. J. Gen. Pract. 68, 143–144 (2018).
  25. Topol, E. J. High-performance medicine: the convergence of human and artificial intelligence. Nat. Med. 25, 44–56 (2019).
  26. FDA. Proposed Regulatory Framework for Modifications to Artificial Intelligence/Machine Learning (AI/ML)-Based Software as a Medical Device (SaMD) - Discussion Paper and Request for Feedback. https://www.regulations.gov/document/FDA-2019-N-1185-0001 (2019).